Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 908 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.3709. Min Act: -0.1700

Data Index: 298036 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.3084. Min Act: -0.1700

Data Index: 215791 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.3709. Min Act: -0.1700

Data Index: 1469114 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.2459. Min Act: -0.1700

Data Index: 897835 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.1834. Min Act: -0.1700

Data Index: 1098692 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.2459. Min Act: -0.1700

Data Index: 57938 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.1834. Min Act: -0.1700

Data Index: 79342 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.1522. Min Act: -0.1700

Data Index: 340075 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.0897. Min Act: -0.1700

Data Index: 1158589 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.0897. Min Act: -0.1700

Data Index: 1060794 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.0897. Min Act: -0.1700

Data Index: 792779 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.0897. Min Act: -0.1700

Data Index: 86635 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.0584. Min Act: -0.1700

Data Index: 648989 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 5.3709. Min Range: -5.3709

Max Act: 4.9959. Min Act: -0.1700

Data Index: 182358 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 5.3709. Min Range: -5.3709

Max Act: 4.9959. Min Act: -0.1700

Data Index: 95790 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.0272. Min Act: -0.1700

Data Index: 1024321 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 5.3709. Min Range: -5.3709

Max Act: 5.0584. Min Act: -0.1700

Data Index: 904853 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 5.3709. Min Range: -5.3709

Max Act: 4.9959. Min Act: -0.1700

Data Index: 1089512 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 5.3709. Min Range: -5.3709

Max Act: 4.9959. Min Act: -0.1700

Data Index: 1096930 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 5.3709. Min Range: -5.3709

Max Act: 4.9959. Min Act: -0.1700

Data Index: 88545 (C4 (Web Text))

Max Activating Token Index: 284